© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70755
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anmar
    -1.36
     bluza
    -1.34
    明け
    -1.27
     Tän
    -1.26
     וכו
    -1.25
     Kullan
    -1.24
     what
    -1.23
    ющийся
    -1.21
    osob
    -1.20
    kijken
    -1.19
    POSITIVE LOGITS
     is
    1.63
     also
    1.58
     was
    1.38
    u
    1.35
    ll
    1.30
    があり
    1.25
     will
    1.23
     has
    1.22
    ra
    1.20
    ha
    1.20
    Activations Density 0.000%

    No Known Activations